Pinned Loading

1. hvm-1 hvm-1 Public

   Video models trained on ~5k hours of human-like video data

   Python 5 1

2. humanlike-vits humanlike-vits Public

   ViT models pretrained with up to ~5k hours of human-like video data

   Python 14

3. optimized-stmae optimized-stmae Public

   An optimized implementation of spatiotemporal masked autoencoders

   Python

4. optimized-mae optimized-mae Public

   An optimized implementation of masked autoencoders (MAEs)

   Python 1 1

5. silicon-menagerie silicon-menagerie Public

   Menagerie of models trained on SAYCam (and more)

   Python 20 5

6. llm-memory llm-memory Public

   Memory experiments with LLMs

   Python 9 1